Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense

• URL: http://arxiv.org/abs/2510.16259v1
• Date: Fri, 17 Oct 2025 23:16:34 GMT
• Title: Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense
• Authors: Zhehao Zhang, Weijie Xu, Shixian Cui, Chandan K. Reddy,
• Abstract summary: We analyze a critical vulnerability we term reasoning distraction, where LRMs are diverted from their primary objective by irrelevant yet complex tasks maliciously embedded in the prompt.<n>We show that even state-of-the-art LRMs are highly susceptible, with injected distractors reducing task accuracy by up to 60%.<n>We propose a training-based defense that combines Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on synthetic adversarial data, improving robustness by over 50 points on challenging distractor attacks.
• Score: 16.519353449118814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a critical vulnerability we term reasoning distraction, where LRMs are diverted from their primary objective by irrelevant yet complex tasks maliciously embedded in the prompt. Through a comprehensive study across diverse models and benchmarks, we show that even state-of-the-art LRMs are highly susceptible, with injected distractors reducing task accuracy by up to 60%. We further reveal that certain alignment techniques can amplify this weakness and that models may exhibit covert compliance, following hidden adversarial instructions in reasoning while concealing them in the final output. To mitigate these risks, we propose a training-based defense that combines Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on synthetic adversarial data, improving robustness by over 50 points on challenging distractor attacks. Our findings establish reasoning distraction as a distinct and urgent threat to LRM reliability and provide a practical step toward safer and more trustworthy reasoning systems.

Related papers

• On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs [15.301640007799735]
  We show that simple, controlled textual perturbations--misleading captions or incorrect chain-of-thought (CoT) traces--cause substantial drops in robustness and confidence.<n>To better understand these vulnerabilities, we analyze RL fine-tuning dynamics and uncover an accuracy-faithfulness trade-off.
  arXiv  Detail & Related papers  (2026-02-13T01:12:00Z)
• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought? [79.86483056611105]
  Reasoning LLMs generate step-by-step chains of thought before giving an answer.<n>How robust are these reasoning traces to disruptions that occur within them?<n>We introduce a controlled evaluation framework that perturbs a model's own CoT at fixed timesteps.
  arXiv  Detail & Related papers  (2026-02-07T10:02:58Z)
• Red Teaming Large Reasoning Models [26.720095252284818]
  Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks.<n>LRMs introduce novel safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies.<n>We propose RT-LRM, a unified benchmark designed to assess the trustworthiness of LRMs.
  arXiv  Detail & Related papers  (2025-11-29T09:45:03Z)
• When Models Outthink Their Safety: Mitigating Self-Jailbreak in Large Reasoning Models with Chain-of-Guardrails [74.63933201261595]
  Large Reasoning Models (LRMs) demonstrate remarkable capabilities on complex reasoning tasks.<n>LRMs remain vulnerable to severe safety risks, including harmful content generation and jailbreak attacks.<n>We propose the Chain-of-Guardrail (CoG), a training framework that recomposes or backtracks unsafe reasoning steps.
  arXiv  Detail & Related papers  (2025-10-24T09:32:25Z)
• One Token Embedding Is Enough to Deadlock Your Large Reasoning Model [91.48868589442837]
  We present the Deadlock Attack, a resource exhaustion method that hijacks an LRM's generative control flow.<n>Our method achieves a 100% attack success rate across four advanced LRMs.
  arXiv  Detail & Related papers  (2025-10-12T07:42:57Z)
• AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models [62.70575022567081]
  We propose AdvChain, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning.<n>Our work establishes a new direction for building more robust and reliable reasoning models.
  arXiv  Detail & Related papers  (2025-09-29T04:27:23Z)
• ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments [18.198349215500183]
  ReasoningGuard injects timely safety aha moments to steer harmless while helpful reasoning processes.<n>Our approach outperforms seven existing safeguards, achieving state-of-the-art safety defenses.
  arXiv  Detail & Related papers  (2025-08-06T08:35:10Z)
• Towards Evaluting Fake Reasoning Bias in Language Models [47.482898076525494]
  We show that models favor the surface structure of reasoning even when the logic is flawed.<n>We introduce THEATER, a benchmark that systematically investigates Fake Reasoning Bias (FRB)<n>We evaluate 17 advanced Large Language Models (LRMs) on both subjective DPO and factual datasets.
  arXiv  Detail & Related papers  (2025-07-18T09:06:10Z)
• Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills [42.1825027925353]
  Large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation.<n>We show that conventional unlearning algorithms, originally designed for non-reasoning models, are inadequate for LRMs.<n>We propose Reasoning-aware Representation Misdirection for Unlearning ($R2MU$), a novel method that effectively suppresses sensitive reasoning traces.
  arXiv  Detail & Related papers  (2025-06-15T20:54:23Z)
• To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models [56.19026073319406]
  Large Reasoning Models (LRMs) are designed to solve complex tasks by generating explicit reasoning traces before producing final answers.<n>We reveal a critical vulnerability in LRMs -- termed Unthinking -- wherein the thinking process can be bypassed by manipulating special tokens.<n>In this paper, we investigate this vulnerability from both malicious and beneficial perspectives.
  arXiv  Detail & Related papers  (2025-02-16T10:45:56Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.